Instructions to use tchbcb/samai-8b-M8 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use tchbcb/samai-8b-M8 with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf tchbcb/samai-8b-M8:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf tchbcb/samai-8b-M8:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf tchbcb/samai-8b-M8:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf tchbcb/samai-8b-M8:Q4_K_M

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf tchbcb/samai-8b-M8:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf tchbcb/samai-8b-M8:Q4_K_M

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf tchbcb/samai-8b-M8:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf tchbcb/samai-8b-M8:Q4_K_M

Use Docker

docker model run hf.co/tchbcb/samai-8b-M8:Q4_K_M

LM Studio
Jan
Ollama
How to use tchbcb/samai-8b-M8 with Ollama:
```
ollama run hf.co/tchbcb/samai-8b-M8:Q4_K_M
```
Unsloth Desktop

How to use tchbcb/samai-8b-M8 with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf tchbcb/samai-8b-M8:Q4_K_M

Configure the model in Pi

# Install Pi:
npm install -g @earendil-works/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "tchbcb/samai-8b-M8:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use tchbcb/samai-8b-M8 with Docker Model Runner:
```
docker model run hf.co/tchbcb/samai-8b-M8:Q4_K_M
```

Lemonade

How to use tchbcb/samai-8b-M8 with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull tchbcb/samai-8b-M8:Q4_K_M

Run and chat with the model

lemonade run user.samai-8b-M8-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use tchbcb/samai-8b-M8 with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf tchbcb/samai-8b-M8:Q4_K_M

Configure Hermes

# Install Hermes:
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
hermes setup
# Point Hermes at the local server:
hermes config set model.provider custom
hermes config set model.base_url http://127.0.0.1:8080/v1
hermes config set model.default tchbcb/samai-8b-M8:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use tchbcb/samai-8b-M8 with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf tchbcb/samai-8b-M8:Q4_K_M

Configure OpenClaw

# Install OpenClaw:
npm install -g openclaw@latest
# Register the local server and set it as the default model:
openclaw onboard --non-interactive --mode local \
  --auth-choice custom-api-key \
  --custom-base-url http://127.0.0.1:8080/v1 \
  --custom-model-id "tchbcb/samai-8b-M8:Q4_K_M" \
  --custom-provider-id llama-cpp \
  --custom-compatibility openai \
  --custom-text-input \
  --accept-risk \
  --skip-health

Run OpenClaw

openclaw agent --local --agent main --message "Hello from Hugging Face"

samai-8b — M8 终版权重 (GGUF)

samai-8b 是基于 Qwen/Qwen3.5-9B（bf16）持续蒸馏增强的对话/执行模型。本仓库交付 M8「agent 执行能力增强」轮的最终 q4_k_m 量化权重，为系列工作的终版交付。

评测结果

评测集	M7 基线	M8 终版	提升
agent60 A 单跳	100.0	100.0	—
agent60 B 多工具	73.3	100.0	+26.7
agent60 C 多轮链式	100.0	93.3	-6.7
agent60 D 负向直答	80.0	93.3	+13.3
agent60 总分	86.7	96.7	+10.0
knight15 能力回归	15/15	15/15	零回退

定靶命中：多工具编排（B +26.7）与负向拒答直答（D +13.3）双双显著提升；knight15 满分确认核心能力零回退。

文件

文件	大小	sha256
`samai8b_m8_q4_k_m.gguf`	5.78 GB (5,780,090,720 B)	`9566d8a7d85782b2284ee970d82306dfd33fb52df4b35e42a722a3d63c94f818`

溯源与训练配方

基座：Qwen/Qwen3.5-9B bf16，逐对校验流式合并 LoRA（128/128 lora pairs 全命中）
训练：QLoRA（nf4, r=32, α=64），教师即程序范式合成的四簇 agent 指令数据（单跳/多工具/多轮链式/负向直答，共 3200 条，含工具可达性红线校验与真答案负样本）
量化链：合并 bf16 → convert_hf_to_gguf.py f16 → llama-quantize q4_k_m
评测：60 题 agent 评测（T4 真机）+ knight15 能力回归门，报告见 m8_final_report.json / m8_knight15_report.json / m8_baseline_report.json

用法 (llama.cpp)

llama-server -m samai8b_m8_q4_k_m.gguf -ngl 99 -c 2048 --port 8080

q4_k_m 在 T4 (SM75) 上验证通过；CPU 模式真推理冒烟亦通过。

PK: samai-8b M8 vs Ternary-Bonsai-2-27B (prism-ml)

同盘位对决 (q4_k_m 5.78G vs PTQ1_0 5.95G), 全新 48 题 agent 任务银行 (零训练泄漏, 四簇: 单跳/多工具/多轮链式/负向直答), 同 harness / 同构 server 配置 / greedy 判分:

簇	samai-8b M8	Bonsai-2-27B	delta
A 单跳	58.3%	58.3%	0
B 多工具	50.0%	41.7%	+8.3
C 多轮链式	41.7%	41.7%	0
D 负向直答	100.0%	100.0%	0
总分	62.5%	60.4%	+2.1

裁决: M8 胜出 — 以 9B/5.78G 打平并在总分与逐题 head-to-head (1 胜 0 负) 上压过 27B/5.95G 的 ternary 同级对手, 多工具编排是决胜簇。逐题明细见 pk_summary.json, 题库见 m8_pk_eval.jsonl。

Downloads last month: -

GGUF

Model size

9B params

Architecture

qwen35

Hardware compatibility

4-bit

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for tchbcb/samai-8b-M8

Base model

Qwen/Qwen3.5-9B-Base

Finetuned

Qwen/Qwen3.5-9B

Quantized

(514)

this model